2 citations · 2 across the 9 of their papers we have counts for
7 papers · 1 filter
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
Katie Kang, Amrith Setlur, Dibya Ghosh +4
Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better und…
Certifiable Reachability Learning Using a New Lipschitz Continuous Value Function
Jingqi Li, Donggun Lee, Jaewon Lee +3
We propose a new reachability learning framework for high-dimensional nonlinear systems, focusing on reach-avoid problems. These problems require computing the reach-avoid set, whi…
Effects of dynamic power electronic load models on power systems analysis using ZIP-E loads
Gabriel E. Colon-Reyes, Reid Dye, Claire Tomlin +1
Power grids are seeing more devices connected at the load level in the form of power electronics: e.g., data centers, electric vehicle chargers, and battery storage facilities. The…
Unfamiliar Finetuning Examples Control How Language Models Hallucinate
Katie Kang, Eric Wallace, Claire Tomlin +2
Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In…
Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations
Jingqi Li, Anand Siththaranjan, Somayeh Sojoudi +2
Autonomous agents should coordinate effectively without prior knowledge of others' intents. While prior work has focused on intent inference, we address the inverse problem: how ag…
The computation of approximate feedback Stackelberg equilibria in multi-player nonlinear constrained dynamic games
Jingqi Li, Somayeh Sojoudi, Claire Tomlin +1
Solving feedback Stackelberg games with nonlinear dynamics and coupled constraints, a common scenario in practice, presents significant challenges. This work introduces an efficien…
Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security
Marsalis Gibson, David Babazadeh, Claire Tomlin +1
Adversarial attacks on learning-based multi-modal trajectory predictors have already been demonstrated. However, there are still open questions about the effects of perturbations o…